A Kinematically Informed Approach to Near-Future Joint Angle Estimation at the Ankle

Abstract

Elevated runtimes of machine learning algorithms and neural networks make their inclusion in near-future joint angle estimation difficult. The purpose of this study was to develop simple, analytical models that prioritize historical joint kinematics when estimating near-future joint angles. Five kinematically-informed and extrapolation-based methods were developed for joint angle estimation at three near-future estimation horizons: $t_{pred} = 50$ ms, 75 ms, and 100 ms. The estimation error and required runtimes of each prediction algorithm were evaluated on the sagittal-plane ankle angles of 24 individual subjects who performed three level-ground walking trials. Results showed that the kinematically-informed models had significantly faster estimation runtimes than Random Forest (RF) machine learning models trained and tested on identical datasets (kinematic models: $t_{run}\lt 0.62$ ms, RF models: $t_{run}\gt 8.19$ ms for all estimation horizons). The RF models exhibited significantly lower prediction errors than the kinematic models for estimation horizons of $t_{pred} = 75$ ms and 100 ms, but no significance was found between the top-performing kinematic model and RF models for a $t_{pred} = 50$ ms. These results indicate that a kinematically-informed approach to joint angle estimation can serve as a simple alternative to complex machine learning models for very near-future applications ( $t_{pred} \leq 50$ ms) while serving as a comparison baseline for more distant estimation horizons ( $t_{pred} \geq 75$ ms).